Multi-layer neural networks using symmetric tensors

Methods and apparatuses for implementing a neural network using symmetric tensors. In embodiments, a system may include a higher order neural network with a plurality of layers that includes an input layer, one or more hidden layers, and an output layer. Each of the input layer, the one or more hidd...

Full description

Saved in:
Bibliographic Details
Main Authors Cruz Vargas, Jesus Adan, Cordourier Maruri, Hector, Zamora Esquivel, Julio, Camacho Perez, Jose, Lopez Meyer, Paulo
Format Patent
LanguageEnglish
Published 20.08.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods and apparatuses for implementing a neural network using symmetric tensors. In embodiments, a system may include a higher order neural network with a plurality of layers that includes an input layer, one or more hidden layers, and an output layer. Each of the input layer, the one or more hidden layers, and the output layer includes a plurality of neurons, where the plurality of neurons includes at least first order neurons and second order neurons, and where inputs at a second order neuron are combined using a symmetric tensor.
Bibliography:Application Number: US202117526628